{"id":"https://openalex.org/W7214909136","doi":"https://doi.org/10.48550/arxiv.2609.37525","title":"Physical Muon: Orthogonalization as an Equilibrium Computation","display_name":"Physical Muon: Orthogonalization as an Equilibrium Computation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214909136","doi":"https://doi.org/10.48550/arxiv.2609.37525"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37525","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37525","pdf_url":"https://arxiv.org/pdf/2609.37525","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37525","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130612119","display_name":"Yuren Hao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao, Yuren","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5130612119"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.38350000977516174,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.38350000977516174,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.38260000944137573,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.08969999849796295,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/orthogonalization","display_name":"orthogonalization","score":0.7459999918937683},{"id":"https://openalex.org/keywords/analog-in-memory-computing","display_name":"analog in-memory computing","score":0.7979999780654907},{"id":"https://openalex.org/keywords/physical-neural-networks","display_name":"physical neural networks","score":0.8180000185966492},{"id":"https://openalex.org/keywords/transformer-training","display_name":"transformer training","score":0.4650000035762787},{"id":"https://openalex.org/keywords/matrix-vector-multiplication","display_name":"matrix-vector multiplication","score":0.6880000233650208},{"id":"https://openalex.org/keywords/rank-1-update","display_name":"rank-1 update","score":0.878000020980835},{"id":"https://openalex.org/keywords/adam","display_name":"Adam","score":0.9909999966621399}],"concepts":[{"id":"https://openalex.org/C47559304","wikidata":"https://www.wikidata.org/wiki/Q1702189","display_name":"Orthogonalization","level":2,"score":0.9825000166893005},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.65420001745224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5278000235557556},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38909998536109924},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C3832189","wikidata":"https://www.wikidata.org/wiki/Q8588916","display_name":"Models of neural computation","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C94766913","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium point","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2660999894142151}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37525","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37525","pdf_url":"https://arxiv.org/pdf/2609.37525","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37525","doi":"https://doi.org/10.48550/arxiv.2609.37525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37525","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37525","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37525","pdf_url":"https://arxiv.org/pdf/2609.37525","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214909136.pdf","grobid_xml":"https://content.openalex.org/works/W7214909136.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1990457366","https://openalex.org/W2037698344","https://openalex.org/W2088307891","https://openalex.org/W2103468298","https://openalex.org/W2307193480","https://openalex.org/W2432567885","https://openalex.org/W2527798464","https://openalex.org/W2797328513","https://openalex.org/W2803163155","https://openalex.org/W2908510526","https://openalex.org/W2964121744","https://openalex.org/W2973506077","https://openalex.org/W3013080934","https://openalex.org/W3191589221","https://openalex.org/W4200611376","https://openalex.org/W4210678178","https://openalex.org/W4385896568","https://openalex.org/W4400235625","https://openalex.org/W4403815243","https://openalex.org/W4405033002","https://openalex.org/W4413946588","https://openalex.org/W4414846785","https://openalex.org/W4415145305","https://openalex.org/W4415798387","https://openalex.org/W4415800764","https://openalex.org/W4416445221","https://openalex.org/W4416606142","https://openalex.org/W7127399853","https://openalex.org/W7133224204","https://openalex.org/W7151471421","https://openalex.org/W7162326533","https://openalex.org/W7164009365","https://openalex.org/W7164969105","https://openalex.org/W7166083486"],"related_works":["https://openalex.org/W7109148841","https://openalex.org/W4414977079","https://openalex.org/W7154373369","https://openalex.org/W7163131241","https://openalex.org/W7161738629","https://openalex.org/W4312220016","https://openalex.org/W7139035261","https://openalex.org/W7166072410","https://openalex.org/W7167049062","https://openalex.org/W4225330564"],"abstract_inverted_index":{"Physical":[0,66],"neural":[1,13],"networks":[2],"and":[3,89,141],"analog":[4,32,44],"in-memory":[5],"computing":[6],"could":[7],"reduce":[8],"the":[9,70,73,82,123,129,138],"energy":[10],"cost":[11],"of":[12,75],"network":[14],"training.":[15],"Realizing":[16],"this":[17,62,96],"potential,":[18],"however,":[19],"requires":[20],"optimizers":[21],"that":[22],"combine":[23],"effective":[24],"learning":[25],"with":[26],"physical":[27],"implementability.":[28],"SGD":[29],"fits":[30],"local":[31,90],"updates":[33],"but":[34,51],"struggles":[35],"on":[36,56,104],"transformers,":[37],"while":[38],"Adam":[39],"family":[40],"is":[41,114,126],"unstable":[42],"against":[43],"bias.":[45],"Muon":[46],"offers":[47],"strong":[48],"training":[49,99,144],"performance,":[50,100],"its":[52],"Newton--Schulz":[53,117],"orthogonalization":[54,71],"relies":[55],"dense":[57,109],"matrix-matrix":[58],"products.":[59],"To":[60,93],"address":[61],"obstacle,":[63],"we":[64,101],"introduce":[65],"Muon,":[67],"which":[68],"computes":[69],"as":[72],"equilibrium":[74],"a":[76,105],"continuous-time":[77],"flow.":[78],"Random":[79],"probes":[80],"approximate":[81],"flow":[83,139],"using":[84],"matrix-vector":[85],"products,":[86],"reciprocal":[87],"reads,":[88],"rank-1":[91],"writes.":[92],"test":[94],"whether":[95],"replacement":[97],"preserves":[98],"evaluate":[102],"it":[103],"10.95M-parameter":[106],"transformer.":[107],"The":[108],"flow's":[110],"mean":[111],"validation":[112],"cross-entropy":[113],"0.0085":[115],"above":[116,128],"across":[118,131],"nine":[119],"seeds":[120],"per":[121],"method;":[122],"probe":[124],"implementation":[125],"0.0188":[127],"control":[130],"two":[132],"seeds.":[133],"Circuit":[134],"simulations":[135],"further":[136],"reproduce":[137],"dynamics":[140],"yield":[142],"comparable":[143],"behavior.":[145]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}